Skill Crossroads devils-advocate
rubric v1.2 · deterministic
A− 92/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 85 1 warn
Clarity & Instructions 100 pass
Token & Context Cost 100 pass
Safety & Security 100 pass
Verifiability & Maintainability 53 1 fail

Top fixes — ranked by score impact

✗ VERIFY-01 Evals or tests present
SKILL.md:1the skill works → no evals/, tests/, or verification section found
No way to prove the skill does what it claims.
Fix Add an evals/ folder (test prompts + expected outcomes) and a '## Verify' step in the body.
⚠ TRIGGER-03 Invocation cues in the description
SKILL.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found
Pure what-it-does prose — the model has to guess when to invoke it.
AI/사람의 결정, 계획, 코드, 설계를 구조화된 프레임워크로 도전하는 비판적 리뷰 레이어. Pre-mortem, Inversion, So…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
★ scores higher than ≈38% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)

Embed this badge

Skill Crossroads grade A− Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/excatt/superclaude-plusplus/skills/devils-advocate.svg)](https://skillcrossroads.com/s/excatt/superclaude-plusplus/skills/devils-advocate)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →